activity
20242026
collaborators

8 papers

cs.CV2026

VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward

Zhaochong An, Orest Kupyn, Théo Uscidda +5

Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting th…

cs.AI2026

The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning

Theo Uscidda, Marta Tintore Gazulla, Maks Ovsjanikov +2

Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks. Existing approaches treat this gap as a kno…

stat.ML2026

Generalized Discrete Diffusion from Snapshots

Oussama Zekri, Théo Uscidda, Nicolas Boullé +1

We introduce Generalized Discrete Diffusion from Snapshots (GDDS), a unified framework for discrete diffusion modeling that supports arbitrary noising processes over large discrete…

cs.AI2025

LATTS: Locally Adaptive Test-Time Scaling

Theo Uscidda, Matthew Trager, Michael Kleinman +3

One common strategy for improving the performance of Large Language Models (LLMs) on downstream tasks involves using a \emph{verifier model} to either select the best answer from a…

cs.LG2025

Disentangled Representation Learning with the Gromov-Monge Gap

Théo Uscidda, Luca Eyring, Karsten Roth +3

Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning. Solving it may unlock other problems, such as generalization, interpretab…

cs.LG2025

GeOT: A spatially explicit framework for evaluating spatio-temporal predictions

Nina Wiedemann, Théo Uscidda, Martin Raubal

When predicting observations across space and time, the spatial layout of errors impacts a model's real-world utility. For instance, in bike sharing demand prediction, error patter…